检索结果-内蒙古大学图书馆

MLFuse: Multi-Scenario Feature Joint Learning for Multi-Modality Image Fusion

IEEE Transactions on Multimedia 2025年

作者： Lei, Jia Li, Jiawei Liu, Jinyuan Wang, Bin Zhou, Shihua Zhang, Qiang Wei, Xiaopeng Kasabov, Nikola K. Dalian University Key Laboratory of Advanced Design and Intelligent Computing Ministry of Education School of Software Engineering Dalian116622 China University of Science and Technology Beijing School of Computer and Communication Engineering Beijing100083 China Dalian University of Technology School of Mechanical Engineering Dalian116024 China Dalian University of Technology School of Computer Science and Technology Dalian116024 China Auckland University of Technology Knowledge Engineering and Discovery Research Institute Auckland1010 New Zealand Ulster University Intelligent Systems Research Center LondonderryBT52 1SA United Kingdom

Multi-modality image fusion (MMIF) entails synthesizing images with detailed textures and prominent objects. Existing methods tend to use general feature extraction to handle different fusion tasks. However, these methods have difficulty breaking fusion barriers across various modalities owing to the lack of targeted learning routes. In this work, we propose a multi-scenario feature joint learning architecture, MLFuse, that employs the commonalities of multi-modality images to deconstruct the fusion progress. Specifically, we construct a cross-modal knowledge reinforcing network that adopts a multipath calibration strategy to promote information communication between different images. In addition, two professional networks are developed to maintain the salient and textural information of fusion results. The spatial-spectral domain optimizing network can learn the vital relationship of the source image context with the help of spatial attention and spectral attention. The edge-guided learning network utilizes the convolution operations of various receptive fields to capture image texture information. The desired fusion results are obtained by aggregating the outputs from the three networks. Extensive experiments demonstrate the superiority of MLFuse for infrared-visible image fusion and medical image fusion. The excellent results of downstream tasks (i.e., object detection and semantic segmentation) further verify the high-quality fusion performance of our method. The code is publicly available at https://***/jialei-sc/MLFuse. © 1999-2012 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

TLSTMF-YOLO: Transfer Learning and Feature Fusion Network for Earthquake-Induced Landslide Detection in Remote Sensing Images

引用

IEEE Transactions on Geoscience and Remote Sensing 2025年 63卷

作者： Meng, Shaoqiang Shi, Zhenming Pirasteh, Saied Liberata Ullo, Silvia Peng, Ming Zhou, Changshi Nunes Goncalves, Wesley Zhang, Limin Tongji University Shanghai Research Institute for Intelligent Autonomous Systems Key Laboratory of Geotechnical and Underground Engineering Ministry of Education Shanghai200092 China Institute of Artificial Intelligence Shaoxing University Zhejiang Shaoxing312000 China Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Geotechnics and Geomatics Tamil Nadu Chennai600 077 India University of Sannio Department of Engineering Benevento82100 Italy Tongji University Shanghai Research Institute for Intelligent Autonomous Systems Shanghai200092 China Federal University of Mato Grosso do Sul Faculty of Computing Campo Grande79070-900 Brazil The Hong Kong University of Science and Technology Department of Civil and Environmental Engineering Hong Kong Hong Kong

Detecting earthquake-induced landslides in remote sensing images is challenging due to the varying sizes of landslides, uneven distribution, and the prevalence of small targets. This study proposes a novel approach, the TLSTMF-YOLO model, which combines a C3-Swin-Transformer and multiscale feature fusion techniques to enhance detection accuracy and efficiency. Key innovations include the use of a convolutional block attention module (CBAM) to improve feature representation, and a bidirectional feature pyramid network (BiFPN) for optimized cross-scale feature fusion. To address data scarcity, a transfer learning strategy is applied, supported by an AdamW optimizer and cosine learning rate strategy for faster convergence. Evaluations on the Jiuzhaigou and Luding landslide datasets demonstrate the model's effectiveness, achieving precision, recall, and mean average precision (mAP)@0.5 of 95.7%, 89.9%, and 90.5% on the Jiuzhaigou dataset, and 96.0%, 90.9%, and 94.5% on the Luding dataset, respectively. In addition, the model processes frames efficiently, with times of 6.61 and 12.2 ms on the two datasets. These results confirm the model's capability for accurate and efficient landslide detection, highlighting its potential for real-world applications. © 1980-2012 IEEE.

关键词： Earthquakes

来源：评论

学校读者我要写书评

暂无评论

A systematic review of explainability in computational intelligence for optimization

引用

Computer Science Review 2025年 57卷

作者： José Almeida João Soares Fernando Lezama Steffen Limmer Tobias Rodemann Zita Vale GECAD - Research Group on Intelligent Engineering and Computing for Advanced Innovation and Development LASI - Intelligent Systems Associate Laboratory ISEP Polytechnic of Porto Porto Portugal HRI-EU – Honda Research Institute Europe Offenbach Germany

This systematic review explores the need for explainability in computational intelligence methods for optimization, such as metaheuristic optimizers, including evolutionary algorithms and swarm intelligence. The work focuses on four aspects: (1) the contribution of Explainable AI (XAI) methods to interpreting metaheuristic performance; (2) the influence of problem features on search behavior and explainability; (3) the role of mathematical theory in providing transparent explanations; and (4) the potential of metaheuristics to enhance the explainability of AI models, such as machine learning (ML). XAI methods such as SHAP, LIME, and visualization techniques provide valuable insights into metaheuristic performance, while landscape analysis and quality diversity approaches reveal algorithm performance across different problem landscapes. The review also explores how metaheuristic algorithms can enhance the interpretability of ML models, turning black-box models into more transparent systems. The work moves on to proposing ”Explainergy,” a novel concept for integrating explainability into metaheuristic algorithms within the energy domain, enhancing the transparency and usability of optimization models. This review is a foundation for future research combining explainability with evolutionary computation and metaheuristic optimization to address real-world challenges in diverse fields, including energy systems.

关键词： Artificial intelligence Black box optimization Computational intelligence Explainability Explainergy Metaheuristics Systematic review

来源：评论

学校读者我要写书评

暂无评论

Dot-base62x: A compact textual representation of IPv6 address for clouds

Dot-base62x: A compact textual representation of IPv6 addres...

引用

4th IEEE/ACM International Conference on Cloud and Utility computing, UCC 2011

作者： Liu, Zhenxing Liu, Lu Hardy, James Anjum, Ashiq Hill, Richard Antonopoulos, Nick Distributed and Intelligent Systems Research Group School of Computing and Mathematics University of Derby Derbyshire United Kingdom

ISBN: (纸本)9780769545929

Cloud computing has dramatically reshaped the whole IT industry in recent years. With the transition from IPv4 to IPv6, services running in Cloud computing will face problems associated with IPv6 addressing: the notation is too long (39 bytes), there are too many variants of a single IPv6 address and a potential conflict may exist with conventional http-URL notation caused by the use of the colon (:). This paper proposes a new scheme to represent an IPv6 address with a shorter, compact notation (27 bytes), without variants or conflicts with http-URL. The proposal is known as dot-base62x as it is an IPv6 address with Base62x and uses the well-known period (or dot) as a group delimiter instead of the colon. The relative merits and demerits of other works that predate this paper have been reviewed and critically evaluated. Cloud computing, as a continuously emerging mainstream of network-based applications, is likely to be a forerunner in the use of IPv6 as the base protocol. As a result, Cloud computing will benefit most from the new, compact and user-friendly textual representation of IPv6 address proposed by this paper. © 2011 IEEE.

关键词： Cloud computing

来源：评论

学校读者我要写书评

暂无评论

Optimizing ranking method using social annotations based on language model

引用

Artificial Intelligence Review 2014年第1期41卷 81-96页

作者： Wen, Kunmei Li, Ruixuan Xia, Jing Gu, Xiwu Intelligent and Distributed Computing laboratory of theHuaZhong University of Science and Technology WuHan China 709th Research Institute China Shipbuilding Industry Corporation WuHan China

Recent research has shown that more and more web users utilize social annotations to manage and organize their interested resources. Therefore, with the growing popularity of social annotations, it is becoming more and more important to utilize such social annotations to achieve effective web search. However, using a statistical model, there are no previous studies that examine the relationships between queries and social annotations. Motivated by this observation, we use social annotations to re-rank search *** intend to optimize retrieval ranking method by using the ranking strategy of integrating the queryannotation similarity into query-document similarity. Specifically, we calculate the queryannotation similarity by using a statistical language model, which in a shorter form we call simply a language model. Then the initial search results are re-ranked according to the computational weighted score of the query-document similarity score and the query-annotation similarity score. Experimental results showthat the proposed method can improve theNDCG score by 8.13%. We further conduct an empirical evaluation of the method by using a query set including about 300 popular social annotations and constructed phrases. More generally, the optimized results with social annotations based on a language model can be of significant benefit to web search.©Springer Science+Business Media B.V. 2011.

关键词： Query processing

来源：评论

学校读者我要写书评

暂无评论

Design and implementation of communication system of the Dawning 6000 supercomputer

引用

中国计算机科学前沿 2010年第4期4卷 466-474页

作者： Qiang LI Bo LI Zhigang HUO Ninghui SUN National Research Center for Intelligent Computing Systems Beijing 100190China Key Laboratory of Computer System and Architecture Chinese Academy of SciencesBeijing 100190China Graduate University of Chinese Academy of Sciences Beijing 100190China National Research Center for Intelligent Computing Systems Beijing 100190China Key Laboratory of Computer System and Architecture Chinese Academy of SciencesBeijing 100190China

An increasing number of supercomputers adopt a heterogeneous architecture, consisting of both general purpose CPUs and specialized accelerators. Such design is beneficial for scalability and power, but on the other hand, heterogeneity brings new challenges in communication systems to connect heterogeneous components and provide support for programming. The communication system of the Dawning 6000 connectstwo kinds of heterogeneous processors, Loongson and AMD, and adopts a three layer architecture with an intranode layer between heterogeneous components. To efficiently connect heterogeneous components, the system forms a global address space and provides a mechanism for message transmission via an in-node global store; and employing Infiniband network, provides an OS-bypassing virtualization method to share an Infiniband card between nodes. To facilitate programming on heterogeneous processors, it supports unified parallel C (UPC), with a modified complier based on global address space. Also, aspecial collective network is implemented for collective operations. Results obtained from a prototype system prove these features to be both feasible and efficient.

关键词： hyper parallel processing (HPP) global address space (GAS) virtualization Dawning 6000 unified parallel C (UPC)

来源：评论

学校读者我要写书评

暂无评论

PEAK: Python-based framework for heterogeneous agent communities

引用

SoftwareX 2025年 30卷

作者： Ribeiro, Bruno Dias, David Gomes, Luis Vale, Zita GECAD - Research Group on Intelligent Engineering and Computing for Advanced Innovation and Development LASI - Intelligent Systems Associate Laboratory Polytechnic of Porto Rua Dr. António Bernardino de Almeida 431 Porto4249-015 Portugal

Python-based framework for heterogeneous agent communities (PEAK) is a multi-agent system development framework aiming at facilitating the interoperability of agents from different environments and their interactions and exchange of knowledge. With PEAK, it is possible to develop from simple agent systems to more complex ones where hundreds of agents, or even thousands, interact with each other to fulfil their purpose. PEAK has contributed to the validation of solutions, published articles and advanced training sessions in different research fields such as energy systems and federated learning. The idea is that, in the future, it will continue to contribute to the enrichment of scientific knowledge in more fields of application. © 2025

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Evaluation of server virtualization technologies for Green IT

Evaluation of server virtualization technologies for Green I...

引用

6th IEEE International Symposium on Service-Oriented System Engineering, SOSE 2011

作者： Liu, Lu Masfary, Osama Li, Jianxin Distributed and Intelligent Systems Research Group School of Computing and Mathematics University of Derby United Kingdom School of Computing Beihang University Beijing China

ISBN: (纸本)9781467304108

Service oriented computing (SOC) and cloud computing paradigm has emerged as an approach which enables ubiquitous, on-demand network accesses to a shared pool of flexibly reconfigurable computing resources. The increasing trends of electrical consumption within data centres are a growing concern for business owners as they are quickly becoming a large fraction of the total cost of ownership. There are several challenges and opportunities within a data centre to lower the electrical costs and improve the energy efficiency. Since servers and air conditioners represent the top users of electrical power in the data centre, this research sets out to explore methods from each subsystem of the data centre as part of an overall energy efficient solution. In this paper, we investigate the current trends of Green IT awareness and how the deployment of IT equipment and Site Infrastructure equipment optimization techniques which can offer a solution to a global issue by reducing carbon emissions. © 2011 IEEE.

关键词： Virtualization

来源：评论

学校读者我要写书评

暂无评论

Nested Named Entity Recognition: A Survey of Latest research

引用

Expert systems 2025年第7期42卷

作者： Ji, Lixia Dang, Yiping Du, Yunlong Gao, Wenzhao Zhang, Han School of Cyber Science and Engineering Zhengzhou University Zhengzhou China College of Computer Science Sichuan University Chengdu China Intelligent Systems Research Centre School of Computing Engineering & Intelligent Systems Ulster University Belfast United Kingdom Intelligent Policing Key Laboratory of Sichuan Province Sichuan Police College Luzhou China

The research on nested named entity recognition (NER) is conducive to providing richer semantic representations and capturing the nested structure among entities, which is crucial for the execution of downstream tasks. This paper aims to summarise the nested NER methods that have been combined with emerging technologies in recent years. We summarise the nested NER methods that are integrated with emerging technologies from three dimensions: model, framework, and data. Additionally, we explore the research progress of nested NER in two scenarios: cross-lingual modality and multi-modal in different modalities. Furthermore, we discuss the practical applications of NER technology in five fields: biomedicine, justice, finance, media, and e-commerce. Through this review, we can clearly see the development trends of nested NER technology under emerging technologies and different modalities, as well as its broad application prospects in various fields. This provides a reference for future exploration directions in nested NER. © 2025 John Wiley & Sons Ltd.

关键词： application fields modal nested named entity recognition new technologies

来源：评论

学校读者我要写书评

暂无评论

PDRL-CM: An efficient cooperative caching management method for vehicular networks based on deep reinforcement learning

引用

Ad Hoc Networks 2025年 176卷

作者： Ou, Pingjie Chen, Ningjiang Yang, Long School of Computer and Electronic Information Guangxi University Nanning Guangxi530004 China Key Laboratory of Parallel Distributed and Intelligent Computing Education Department of Guangxi Zhuang Autonomous Region Nanning Guangxi530004 China The Guangxi Intelligent Digital Services Research Center of Engineering Technology Nanning Guangxi530004 China

In vehicular networks, onboard devices face the challenge of limited storage, and computational resources constrain their processing and storage capabilities. This limitation is particularly significant for applications that require complex computations and real-time responses. Additionally, limited storage capacity reduces the range of cacheable data, which can impact the immediate availability of data and the continuity of services. Therefore, improving cache utilization and meeting vehicles’ real-time data demands pose significant challenges. Deep reinforcement learning can optimize the issues arising from agents’ continuously changing state and action spaces due to increasing request demands. However, training the network may encounter instability and convergence difficulties in dynamic and complex environments or situations with sparse rewards. In response to these issues, this paper proposes a Priority-based Deep Reinforcement Learning Collaborative Cache Management method (PDRL-CM). PDRL-CM first designs a lightweight cache admission strategy that leverages data's inherent and combined attributes. It then makes cache admission decisions Using Monte Carlo sampling and a max-value search strategy combined with a feedforward neural network. Secondly, the method considers minimizing system latency and reducing vehicle energy consumption as joint optimization problems. An improved deep reinforcement learning algorithm solves this problem and makes cache-sharding decisions. A prioritized experience replay mechanism is incorporated to adjust the network prediction model quickly and accelerate the convergence process. Experimental results indicate that, compared to existing DRL-based caching methods, PDRL-CM offers faster data processing efficiency and higher cache hit rates under varying vehicle density, storage capacity, and content volume conditions. © 2025

关键词： Cache memory

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：